johngiorgi commited on
Commit
383ffe4
1 Parent(s): bd7fb21

Link out to the MS2 leaderboard

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # Overview
16
 
17
- This model is a fine-tuned version of [allenai/led-base-16384](https://huggingface.co/allenai/led-base-16384) on the [MS^2](https://github.com/allenai/mslr-shared-task#ms2-dataset) dataset. The model received as input the background section and the titles and abstracts of up to 25 included studies for each example, concatenated by the `"</s>"` token. Global attention is applied to the special start token `"<s>"` and each of the document seperator tokens `"</s>"`. The model slightly outperforms the reported results in the original paper: [MS2: Multi-Document Summarization of Medical Studies](https://arxiv.org/abs/2104.06486).
18
 
19
  It achieves the following results on the evaluation set:
20
  - Loss: 3.7602
14
 
15
  # Overview
16
 
17
+ This model is a fine-tuned version of [allenai/led-base-16384](https://huggingface.co/allenai/led-base-16384) on the [MS^2](https://github.com/allenai/mslr-shared-task#ms2-dataset) dataset. The model received as input the background section and the titles and abstracts of up to 25 included studies for each example, concatenated by the `"</s>"` token. Global attention is applied to the special start token `"<s>"` and each of the document separator tokens `"</s>"`. The model slightly outperforms the reported results in the original paper: [MS2: Multi-Document Summarization of Medical Studies](https://arxiv.org/abs/2104.06486). See the [MS2 leaderboard](https://leaderboard.allenai.org/mslr-ms2/submissions/public) for results on the blind test set.
18
 
19
  It achieves the following results on the evaluation set:
20
  - Loss: 3.7602